Rule.AB2 — two-sided: emotion A falls by >=T while emotion B rises by >=T, each consecutive step <=C Source. trajectories_v5.parquet | Family. one corpus in isolation Sampled from 931 matching rows, without replacement across the family, so no two tiers reuse a chain.
How to read a Script. Each chunk is one line:
a short tag of what the models heard in that clip, then the words spoken.
(underlined, plain ·
delivery, style) — the tag before the words. Emotions first, then how
it is delivered. Underlined descriptors are the ones that change across this chain
— anything identical on every clip is pulled out and stated once above, because a
value that never moves says nothing about a trajectory.
(ahem) — brackets inside the words
are a different thing: a real non-speech sound, printed where it happens. Most clips have
none; about a quarter do.
The full generated caption for any clip is still there, under
“full caption & clip details”. Its perceived-gender and background-noise
clauses were re-rendered from the numeric buckets, because the versions stored in the
corpus index had those two ladders running backwards.
The emotion clause has been re-derived, and it used to be wrong. The 40 emotion heads are not on a common scale — Interest has a median of 2.08 and is never zero, while Infatuation is zero on 87.7 % of clips — and the caption named an emotion whenever its raw score cleared an absolute 1.0. Interest therefore appeared in 94.8 % of captions and Sadness in almost none: the clause was reporting the scale of the head, not the emotion of the clip. An emotion is now named only when it lands in the top 10 % for that emotion, against a pooled tie-aware mid-rank ECDF over 132,833,726 utterances spanning every dataset and language. Interest now appears in 6.2 %, all 40 emotions occur, and a clip that is ordinary on all 40 says “no dominant emotion” rather than being forced to pick one (21.8 % of clips). This is the same scale the trajectory miner selects on, so the caption and the mining now refer to the same quantity: the mined target emotion is named in the final clip's caption on 73 % of chains, up from 46 %.
Contentment ↓ / Concentration ↑c-mls-AB2 · #1
This chain comes from the two-sided rule: it only counts if both emotions move — Contentment down and Concentration up — by at least 0.25 each.
The chain starts with Concentration clearly present — 0.64, higher than 64 % of clips in this corpus — and ends with it at the very top of the corpus at 0.95, higher than 95 % of clips in this corpus. That is a total rise of 0.31.
At the same time Contentment goes the other way, from 0.93 (higher than 93 % of clips in this corpus) to 0.56 (higher than 56 % of clips in this corpus), a change of -0.36. Both halves had to happen for this chain to qualify.
It takes 4 clips to get there. Clip to clip the moves are +0.07, then +0.13, then +0.12 — a fairly even climb, though some clips carry more of the change than others.
No single step is larger than the 0.25 cap, which is exactly what stops this being a jump cut: the change has to be spread across the clips instead of landing all at once.
Same speaker? The least similar clip scores 0.94 against the first clip, where 1.00 would mean an identical voice. That is a strong match — almost certainly one person throughout. Neighbouring clips score at worst 0.96 against each other.
Voice consistency: these clips are separate recordings joined together. The measured match is tight (0.94), so any shift should be subtle — but you may still notice the voice change slightly from segment to segment. Voice conversion has not been applied yet in this build. A planned pass will re-render every segment onto the first segment's voice, which removes this effect entirely.
4 clips · 67 s · polish · mls
hear it un-normalised (raw levels, max seam 0.4 dB)
Unchanged across all 4 clips: a child masculine voice · neutral-toned, neutral-bright, fairly smooth, balanced body, good recording, quiet background, normal-paced, normally alert
(contentment, triumph · some disfluency, monologue, narration)wąska kanapka obita skórą dwa krzesła również skórą obite duża blaszana miednica i mała szafa ciemnowiśniowej barwy stanowiły umeblowanie pokoju który ze względu na swoję długość i mrok w nim panujący zdawał się być podobniejszym do grobu aniżeli do mieszkania
full caption & clip details
A child masculine voice; delivery is normally alert, normal-paced, slightly relaxed, fairly steady; timbre is neutral-toned, neutral-bright, fairly smooth, balanced body; average clarity, some disfluency, moderate pitch range, light breath; affect is neutral, neutral stance, slightly guarded; reads as contentment, triumph; style: monologue, narration; good recording, quiet background; genuineness 0.3/6; vocal-burst blend 3.1/10; 18.4s, POLISH.
6892_8764_000241 · in -26.2 dBFS · gain +6.2 dB · mls-00111
(pride, malevolence malice, shame· some disfluency, narration, monologue)równie jak pokój nie zmieniły się od ćwierć wieku zwyczaje pana ignacego rano budził się zawsze o szóstej przez chwilę słuchał czy idzie leżący na krześle zegarek i spoglądał na skazówki które tworzyły jednę linią prostą
full caption & clip details
A child masculine voice; delivery is normally alert, normal-paced, slightly relaxed, fairly steady; timbre is neutral-toned, neutral-bright, fairly smooth, balanced body; average clarity, some disfluency, moderate pitch range, light breath; affect is neutral, neutral stance, slightly guarded; reads as pride, malevolence malice, shame; style: narration, monologue; good recording, quiet background; genuineness 0.7/6; vocal-burst blend 1.1/10; 14.8s, POLISH.
6892_8764_000148 · in -26.7 dBFS · gain +6.7 dB · mls-00111
(triumph, relief·almost no disfluency, narration, monologue)chciał wstać spokojnie bez awantur ale że chłodne nogi i nieco zesztywniałe ręce nie okazywały się dość uległemi jego woli więc zrywał się nagle wyskakiwał na środek pokoju i rzuciwszy na łóżko szlafmycę biegł pod piec do wielkiej miednicy
full caption & clip details
A child masculine voice; delivery is normally alert, normal-paced, slightly relaxed, fairly steady; timbre is neutral-toned, neutral-bright, fairly smooth, balanced body; average clarity, almost no disfluency, moderate pitch range, light breath; affect is neutral, neutral stance, slightly guarded; reads as triumph, relief; style: narration, monologue; good recording, quiet background; genuineness 0.3/6; vocal-burst blend 2.7/10; 15.6s, POLISH.
6892_8764_001691 · in -26.3 dBFS · gain +6.3 dB · mls-00111
(concentration, interest·some disfluency, narration, monologue)w której mył się od stóp do głów rżąc i parskając jak wiekowy rumak szlachetnej krwi któremu przypomniał się wyścig podczas obrządku wycierania się kosmatemi ręcznikami z upodobaniem patrzał na swoje chude łydki i zarośnięte piersi mrucząc no przecie nabieram ciała
full caption & clip details
A young adult masculine voice; delivery is normally alert, normal-paced, slightly relaxed, fairly steady; timbre is neutral-toned, neutral-bright, fairly smooth, balanced body; average clarity, some disfluency, moderate pitch range, light breath; affect is neutral, neutral stance, slightly guarded; reads as concentration, interest; style: narration, monologue; good recording, quiet background; genuineness 0.0/6; vocal-burst blend 2.7/10; 17.7s, POLISH.
6892_8764_000379 · in -26.6 dBFS · gain +6.6 dB · mls-00111
Jealousy and Envy ↓ / Emotional Numbness ↑c-mls-AB2 · #2
This chain comes from the two-sided rule: it only counts if both emotions move — Jealousy and Envy down and Emotional Numbness up — by at least 0.25 each.
The chain starts with Emotional Numbness clearly present — 0.73, higher than 73 % of clips in this corpus — and ends with it at the very top of the corpus at 0.98, higher than 98 % of clips in this corpus. That is a total rise of 0.25.
At the same time Jealousy and Envy goes the other way, from 0.97 (higher than 97 % of clips in this corpus) to 0.53 (higher than 53 % of clips in this corpus), a change of -0.44. Both halves had to happen for this chain to qualify.
It takes 5 clips to get there. Clip to clip the moves are +0.09, then +0.18, then -0.04, then +0.03 — not a clean run: step 3 moves back the other way by 0.04 before the chain recovers.
No single step is larger than the 0.25 cap, which is exactly what stops this being a jump cut: the change has to be spread across the clips instead of landing all at once.
Same speaker? The least similar clip scores 0.92 against the first clip, where 1.00 would mean an identical voice. That is a strong match — almost certainly one person throughout. Neighbouring clips score at worst 0.94 against each other.
Voice consistency: these clips are separate recordings joined together. The measured match is tight (0.92), so any shift should be subtle — but you may still notice the voice change slightly from segment to segment. Voice conversion has not been applied yet in this build. A planned pass will re-render every segment onto the first segment's voice, which removes this effect entirely.
5 clips · 76 s · spanish · mls
hear it un-normalised (raw levels, max seam 0.4 dB)
Unchanged across all 5 clips: a young adult masculine voice · neutral-toned, balanced body, measured, slightly relaxed, steady, fairly narrow pitch
(jealousy and envy, contentment, disgust · subdued, no disfluency, slurred, narration)quisiera que hubieras estado allí para observar la maniobra y eso de decir que al capitán le gustan igualmente enriqueta y luisa es tonto porque le gusta sin duda enriqueta mucho más
full caption & clip details
A young adult masculine voice; delivery is subdued, measured, slightly relaxed, steady; timbre is neutral-toned, slightly dark, fairly smooth, balanced body; slurred, no disfluency, fairly narrow pitch, light breath; affect is neutral, neutral stance, slightly guarded; reads as jealousy and envy, contentment, disgust; style: narration, monologue; good recording, quiet background; genuineness 0.1/6; vocal-burst blend 0.4/10; 13.3s, SPANISH.
12367_11991_000132 · in -26.4 dBFS · gain +6.3 dB · mls-00039
(disappointment, bitterness, anger· subdued, some disfluency, somewhat unclear, monologue)pero este carlos es tan prosaico me hubiera gustado que estuvieras con nosotras ayer tarde para haber juzgado por ti misma y estoy segura de que pensarías como yo a menos de que quisieras llevarme la contraria conque ana asistiera a la comida en casa de
full caption & clip details
An adult masculine voice; delivery is subdued, measured, slightly relaxed, steady; timbre is neutral-toned, neutral-bright, slightly rough, balanced body; somewhat unclear, some disfluency, fairly narrow pitch, light breath; affect is mildly negative, neutral stance, slightly guarded; reads as disappointment, bitterness, anger; style: monologue, whispered; average recording, quiet background; genuineness 1.3/6; vocal-burst blend 5.5/10; 19.2s, SPANISH.
12367_11991_000126 · in -26.3 dBFS · gain +6.3 dB · mls-00039
(emotional numbness, fatigue exhaustion, contentment·normally alert, no disfluency, slurred, monologue)le hubiera bastado para observar todas estas cosas pero se quedó en casa con un pretexto en el que se complicaban un dolor de cabeza y un retroceso en la enfermedad de carlitos
full caption & clip details
An adult masculine voice; delivery is normally alert, measured, slightly relaxed, steady; timbre is neutral-toned, neutral-bright, fairly smooth, balanced body; slurred, no disfluency, fairly narrow pitch, minimal breath; affect is neutral, neutral stance, slightly guarded; reads as emotional numbness, fatigue exhaustion, contentment; style: monologue, whispered; average recording, no background noise; genuineness 0.1/6; vocal-burst blend 1.7/10; 13.6s, SPANISH.
12367_11991_000080 · in -26.4 dBFS · gain +6.4 dB · mls-00039
(emotional numbness, triumph, contentment ·subdued, no disfluency, somewhat unclear, narration)era su único propósito evitar al capitán wentwortfa pero el resultado había sido eludir el ser tomada como árbitro al mismo tiempo que disfrutar de una tarde tranquila
full caption & clip details
An adult masculine voice; delivery is subdued, measured, slightly relaxed, steady; timbre is neutral-toned, neutral-bright, fairly smooth, balanced body; somewhat unclear, no disfluency, fairly narrow pitch, light breath; affect is neutral, neutral stance, slightly guarded; reads as emotional numbness, triumph, contentment; style: narration, monologue; good recording, no background noise; genuineness 0.0/6; vocal-burst blend 1.8/10; 13.1s, SPANISH.
12367_11991_000077 · in -26.8 dBFS · gain +6.8 dB · mls-00039
(emotional numbness, malevolence malice, thankfulness gratitude· subdued, almost no disfluency, somewhat unclear, monologue)respecto a los designios del capitán wentworth pensaba ella que debía importar más a federico resolver pronto su preferencia si no quería comprometer ja felicidad de las dos muchachas o desdorar su propio honor
full caption & clip details
An adult masculine voice; delivery is subdued, measured, slightly relaxed, steady; timbre is neutral-toned, slightly dark, fairly smooth, balanced body; somewhat unclear, almost no disfluency, fairly narrow pitch, light breath; affect is neutral, neutral stance, slightly guarded; reads as emotional numbness, malevolence malice, thankfulness gratitude; style: monologue, narration; average recording, quiet background; genuineness 0.1/6; vocal-burst blend 1.7/10; 16.3s, SPANISH.
12367_11991_000025 · in -26.5 dBFS · gain +6.5 dB · mls-00039
Pride ↓ / Contempt ↑c-mls-AB2 · #3
This chain comes from the two-sided rule: it only counts if both emotions move — Pride down and Contempt up — by at least 0.25 each.
The chain starts with Contempt clearly present — 0.71, higher than 71 % of clips in this corpus — and ends with it at the very top of the corpus at 0.98, higher than 98 % of clips in this corpus. That is a total rise of 0.27.
At the same time Pride goes the other way, from 0.97 (higher than 97 % of clips in this corpus) to 0.66 (higher than 66 % of clips in this corpus), a change of -0.31. Both halves had to happen for this chain to qualify.
It takes 3 clips to get there. Clip to clip the moves are +0.15, then +0.12 — an even, steady climb — each clip carries about the same share.
No single step is larger than the 0.25 cap, which is exactly what stops this being a jump cut: the change has to be spread across the clips instead of landing all at once.
Same speaker? The least similar clip scores 0.94 against the first clip, where 1.00 would mean an identical voice. That is a strong match — almost certainly one person throughout. Neighbouring clips score at worst 0.94 against each other.
Voice consistency: these clips are separate recordings joined together. The measured match is tight (0.94), so any shift should be subtle — but you may still notice the voice change slightly from segment to segment. Voice conversion has not been applied yet in this build. A planned pass will re-render every segment onto the first segment's voice, which removes this effect entirely.
3 clips · 44 s · spanish · mls
hear it un-normalised (raw levels, max seam 1.7 dB)
Unchanged across all 3 clips: a child feminine voice · neutral-toned, neutral-bright, fairly smooth, normally alert, slightly relaxed, fairly steady, clear, moderate pitch range
(pride · measured, no disfluency, narration, monologue)en este punto el maestro de escuela impugnó igualmente el sermón y defendió con más calor ahinco y acierto á juanita es decía una muchacha discreta honrada y trabajadora
full caption & clip details
A child feminine voice; delivery is normally alert, measured, slightly relaxed, fairly steady; timbre is neutral-toned, neutral-bright, fairly smooth, balanced body; clear, no disfluency, moderate pitch range, light breath; affect is neutral, neutral stance, slightly guarded; reads as pride; style: narration, monologue; good recording, quiet background; genuineness 0.8/6; vocal-burst blend 1.8/10; 15.5s, SPANISH.
10246_11832_000209 · in -26.6 dBFS · gain +6.7 dB · mls-00038
(anger, sourness, shame·normal-paced, almost no disfluency, narration, cartoonish)dios la ha hecho hermosísima y casi estoy por decir que no sólo tiene derecho sino que tiene el deber de acicalarse y de realzar y mostrar la hermosura que dios le ha dado lo contrario sería ingratitud para con dios y desdeñar lo que enseña la parábola de los cinco talentos
full caption & clip details
A young adult feminine voice; delivery is normally alert, normal-paced, slightly relaxed, fairly steady; timbre is neutral-toned, neutral-bright, fairly smooth, thin; clear, almost no disfluency, moderate pitch range, light breath; affect is neutral, neutral stance, slightly guarded; reads as anger, sourness, shame; style: narration, cartoonish; average recording, no background noise; genuineness 1.3/6; vocal-burst blend 5.0/10; 16.7s, SPANISH.
10246_11832_001044 · in -25.0 dBFS · gain +5.0 dB · mls-00038
(contempt, astonishment surprise, malevolence malice· normal-paced, almost no disfluency, authoritative, monologue)talentos y extraño mucho que ustedes que han estado conmigo de fendiendo la propiedad individual se vuelvan aho ra contra mí y se pongan del lado de don policarpo para impugnar dicha propiedad
full caption & clip details
A young adult feminine voice; delivery is normally alert, normal-paced, slightly relaxed, fairly steady; timbre is neutral-toned, neutral-bright, fairly smooth, balanced body; clear, almost no disfluency, moderate pitch range, light breath; affect is neutral, neutral stance, slightly guarded; reads as contempt, astonishment surprise, malevolence malice; style: authoritative, monologue; good recording, no background noise; genuineness 0.4/6; vocal-burst blend 1.6/10; 11.3s, SPANISH.
10246_11832_000488 · in -24.4 dBFS · gain +4.3 dB · mls-00038
Contempt ↓ / Emotional Numbness ↑c-mls-AB2 · #4
This chain comes from the two-sided rule: it only counts if both emotions move — Contempt down and Emotional Numbness up — by at least 0.25 each.
The chain starts with Emotional Numbness clearly present — 0.72, higher than 72 % of clips in this corpus — and ends with it at the very top of the corpus at 1.00, virtually no clip in this corpus scores higher. That is a total rise of 0.28.
At the same time Contempt goes the other way, from 0.98 (higher than 98 % of clips in this corpus) to 0.50 (right about the corpus median), a change of -0.48. Both halves had to happen for this chain to qualify.
It takes 4 clips to get there. Clip to clip the moves are +0.20, then -0.10, then +0.17 — not a clean run: step 2 moves back the other way by 0.10 before the chain recovers.
No single step is larger than the 0.25 cap, which is exactly what stops this being a jump cut: the change has to be spread across the clips instead of landing all at once.
Same speaker? The least similar clip scores 0.95 against the first clip, where 1.00 would mean an identical voice. That is a strong match — almost certainly one person throughout. Neighbouring clips score at worst 0.96 against each other.
Voice consistency: these clips are separate recordings joined together. The measured match is tight (0.95), so any shift should be subtle — but you may still notice the voice change slightly from segment to segment. Voice conversion has not been applied yet in this build. A planned pass will re-render every segment onto the first segment's voice, which removes this effect entirely.
4 clips · 62 s · french · mls
hear it un-normalised (raw levels, max seam 1.2 dB)
Unchanged across all 4 clips: a young adult feminine voice · neutral-toned, neutral-bright, fairly smooth, balanced body, good recording, no background noise, normally alert, slightly relaxed
(contempt, sourness, awe · normal-paced, moderate pitch range, monologue, narration)om carlos est aussi un ouvrage de la jeunesse de schiller et cependant on le considère comme une composition du premier rang ce sujet de don carlos est un des plus dramatiques que l'histoire puisse offrir
full caption & clip details
A young adult feminine voice; delivery is normally alert, normal-paced, slightly relaxed, steady; timbre is neutral-toned, neutral-bright, fairly smooth, balanced body; clear, no disfluency, moderate pitch range, light breath; affect is neutral, neutral stance, slightly guarded; reads as contempt, sourness, awe; style: monologue, narration; good recording, no background noise; genuineness 0.0/6; vocal-burst blend 0.1/10; 13.0s, FRENCH.
12709_13781_004667 · in -26.4 dBFS · gain +6.4 dB · mls-00055
(sourness, awe, malevolence malice· normal-paced, fairly narrow pitch, monologue, narration)une jeune princesse fille de henri ï quitte la france et la cour brillante et chevaleresque du roi son père pour s'unir à un vieux tyran tellement sombre et sévère que le caractère même des espagnols fut altéré par son règne et que pendant longtemps la nation porta l'empreinte de son maître
full caption & clip details
A young adult feminine voice; delivery is normally alert, normal-paced, slightly relaxed, steady; timbre is neutral-toned, neutral-bright, fairly smooth, balanced body; clear, no disfluency, fairly narrow pitch, light breath; affect is neutral, neutral stance, slightly guarded; reads as sourness, awe, malevolence malice; style: monologue, narration; good recording, no background noise; genuineness 0.0/6; vocal-burst blend 0.2/10; 18.6s, FRENCH.
12709_13781_004091 · in -26.2 dBFS · gain +6.2 dB · mls-00055
(pain, sadness, fear·measured, fairly narrow pitch, monologue, narration)carlos fiancé d'abord à élisabeth l'aime encore quoiqu'elle soit devenue sa belle-mère la réformation et la révolte des paysbas ces grands événements politiques se mêlent à la catastrophe tragique de la condamnation du fils par le père
full caption & clip details
A young adult feminine voice; delivery is normally alert, measured, slightly relaxed, steady; timbre is neutral-toned, neutral-bright, fairly smooth, balanced body; clear, no disfluency, fairly narrow pitch, light breath; affect is neutral, neutral stance, slightly guarded; reads as pain, sadness, fear; style: monologue, narration; good recording, no background noise; genuineness 0.0/6; vocal-burst blend 0.1/10; 16.0s, FRENCH.
12709_13781_005073 · in -27.4 dBFS · gain +7.4 dB · mls-00055
(emotional numbness· measured, fairly narrow pitch, monologue, newsreading)l'intérêt individuel et l'intérêt pumic se trouvent réunis au plus haut degré dans cette tragédie plusieurs écrivains ont traité ce sujet en france mais on n'a pu dans l'ancien régime le mettre sur le théâtre
full caption & clip details
A young adult feminine voice; delivery is normally alert, measured, slightly relaxed, steady; timbre is neutral-toned, neutral-bright, fairly smooth, balanced body; clear, no disfluency, fairly narrow pitch, light breath; affect is neutral, neutral stance, slightly guarded; reads as emotional numbness; style: monologue, newsreading; good recording, no background noise; genuineness 0.0/6; vocal-burst blend 0.0/10; 14.3s, FRENCH.
12709_13781_004997 · in -27.0 dBFS · gain +7.0 dB · mls-00055
Concentration ↓ / Shame ↑c-mls-AB2 · #5
This chain comes from the two-sided rule: it only counts if both emotions move — Concentration down and Shame up — by at least 0.25 each.
The chain starts with Shame clearly present — 0.64, higher than 64 % of clips in this corpus — and ends with it at the very top of the corpus at 0.98, higher than 98 % of clips in this corpus. That is a total rise of 0.34.
At the same time Concentration goes the other way, from 0.97 (higher than 97 % of clips in this corpus) to 0.67 (higher than 67 % of clips in this corpus), a change of -0.30. Both halves had to happen for this chain to qualify.
It takes 4 clips to get there. Clip to clip the moves are +0.19, then +0.00, then +0.15 — most of the change happening immediately, then levelling off.
No single step is larger than the 0.25 cap, which is exactly what stops this being a jump cut: the change has to be spread across the clips instead of landing all at once.
Same speaker? The least similar clip scores 0.82 against the first clip, where 1.00 would mean an identical voice. That is above the 0.80 threshold the mining used — very likely one person. Neighbouring clips score at worst 0.82 against each other.
Voice consistency: these clips are separate recordings joined together, matching at 0.82. You may notice the voice shift a little between segments. Voice conversion has not been applied yet in this build. A planned pass will re-render every segment onto the first segment's voice, which removes this effect entirely.
4 clips · 55 s · dutch · mls
hear it un-normalised (raw levels, max seam 0.7 dB)
Unchanged across all 4 clips: an elderly masculine voice · neutral-toned, slightly dark, average recording, quiet background, measured, normally alert, slightly relaxed, fairly steady
(concentration, impatience and irritability · frequent disfluency, wide pitch range, audible breath, cartoonish)neen zeide mevrouw aarssen dat ware niet raadzaam geweest want zoo als de dafnis zegt in de minneklacht hier zeit u de ronde sta daer de schildwacht
full caption & clip details
An elderly masculine voice; delivery is normally alert, measured, slightly relaxed, fairly steady; timbre is neutral-toned, slightly dark, rough, thin; slurred, frequent disfluency, wide pitch range, audible breath; affect is neutral, neutral stance, slightly guarded; reads as concentration, impatience and irritability; style: cartoonish, storytelling; average recording, quiet background; genuineness 1.8/6; vocal-burst blend 0.7/10; 15.0s, DUTCH.
2450_10026_003886 · in -29.1 dBFS · gain +9.1 dB · mls-00085
(malevolence malice, emotional numbness, concentration ·some disfluency, fairly narrow pitch, audible breath, narration)en zoo vervolgde sylvius bleef ik te scheveningen en zond u heden middag onzen getrouwen maarten ten einde te vernemen of de zaak in orde ware
full caption & clip details
An elderly masculine voice; delivery is normally alert, measured, slightly relaxed, fairly steady; timbre is neutral-toned, slightly dark, rough, thin; slurred, some disfluency, fairly narrow pitch, audible breath; affect is neutral, slightly dominant, slightly guarded; reads as malevolence malice, emotional numbness, concentration; style: narration, monologue; average recording, quiet background; genuineness 0.9/6; vocal-burst blend 0.4/10; 11.0s, DUTCH.
2450_10026_002890 · in -28.4 dBFS · gain +8.4 dB · mls-00084
(malevolence malice, emotional numbness, concentration · some disfluency, fairly narrow pitch, audible breath, narration)en zoo vervolgde sylvius bleef ik te scheveningen en zond u heden middag onzen getrouwen maarten ten einde te vernemen of de zaak in orde ware
full caption & clip details
An elderly masculine voice; delivery is normally alert, measured, slightly relaxed, fairly steady; timbre is neutral-toned, slightly dark, rough, thin; slurred, some disfluency, fairly narrow pitch, audible breath; affect is neutral, slightly dominant, slightly guarded; reads as malevolence malice, emotional numbness, concentration; style: narration, monologue; average recording, quiet background; genuineness 0.9/6; vocal-burst blend 0.4/10; 11.0s, DUTCH.
2450_10026_002890 · in -28.4 dBFS · gain +8.4 dB · mls-00084
(shame, jealousy and envy, disappointment·frequent disfluency, wide pitch range, normal breath, cartoonish)en zijt gy alleen gekomen vroeg buat en hoe hebt gy het op reis gehad vroeg zijn vrouw veroorlooft my een voor een uwe vragen te beantwoorden zeide sylvius mevrouw doet my de eer aan my te vragen hoe ik het gehad heb
full caption & clip details
A middle-aged masculine voice; delivery is normally alert, measured, slightly relaxed, fairly steady; timbre is neutral-toned, slightly dark, slightly rough, balanced body; slurred, frequent disfluency, wide pitch range, normal breath; affect is neutral, neutral stance, slightly guarded; reads as shame, jealousy and envy, disappointment; style: cartoonish, didactic; average recording, quiet background; genuineness 1.7/6; vocal-burst blend 0.8/10; 17.5s, DUTCH.
2450_10026_000162 · in -28.9 dBFS · gain +8.9 dB · mls-00084
Disgust ↓ / Contemplation ↑c-mls-AB2 · #6
This chain comes from the two-sided rule: it only counts if both emotions move — Disgust down and Contemplation up — by at least 0.25 each.
The chain starts with Contemplation clearly present — 0.64, higher than 64 % of clips in this corpus — and ends with it at the very top of the corpus at 0.99, higher than 99 % of clips in this corpus. That is a total rise of 0.36.
At the same time Disgust goes the other way, from 0.98 (higher than 98 % of clips in this corpus) to 0.65 (higher than 65 % of clips in this corpus), a change of -0.33. Both halves had to happen for this chain to qualify.
It takes 3 clips to get there. Clip to clip the moves are +0.23, then +0.13 — a fairly even climb, though some clips carry more of the change than others.
No single step is larger than the 0.25 cap, which is exactly what stops this being a jump cut: the change has to be spread across the clips instead of landing all at once.
Same speaker? The least similar clip scores 0.95 against the first clip, where 1.00 would mean an identical voice. That is a strong match — almost certainly one person throughout. Neighbouring clips score at worst 0.93 against each other.
Voice consistency: these clips are separate recordings joined together. The measured match is tight (0.95), so any shift should be subtle — but you may still notice the voice change slightly from segment to segment. Voice conversion has not been applied yet in this build. A planned pass will re-render every segment onto the first segment's voice, which removes this effect entirely.
Unchanged across all 3 clips: a young adult feminine voice · neutral-toned, neutral-bright, fairly smooth, balanced body, good recording, measured, normally alert, slightly relaxed
(disgust, sadness, shame · formal, monologue)il se fût agi d'aller à la messe de paroisse que leur mise n'eût été pas plus décente seuls les gros cache-nez de couleurs vives noués sur la gorge et les vestes de bure jetées sur l'épaule en guise de pardessus avertissaient du voisinage des pays arctiques quand tu voudras jean rené prononça le capitaine
full caption & clip details
A young adult feminine voice; delivery is normally alert, measured, slightly relaxed, steady; timbre is neutral-toned, neutral-bright, fairly smooth, balanced body; clear, no disfluency, fairly narrow pitch, light breath; affect is neutral, neutral stance, slightly guarded; reads as disgust, sadness, shame; style: formal, monologue; good recording, quiet background; genuineness 0.0/6; vocal-burst blend 0.6/10; 19.8s, FRENCH.
12709_14178_000618 · in -29.5 dBFS · gain +9.5 dB · mls-00057
(emotional numbness, pain, sadness ·narration, monologue)je soulevai mon bonnet de fourrure aux trois quarts pelé et je commençai le signe de la croix en hanô an tad hag ar mab har ar spéred santel ailleurs la scène eût peut-être passé pour drôle et j'aurais probablement fait l'effet d'un singulier curé
full caption & clip details
A child feminine voice; delivery is normally alert, measured, slightly relaxed, steady; timbre is neutral-toned, neutral-bright, fairly smooth, balanced body; clear, no disfluency, fairly narrow pitch, light breath; affect is neutral, neutral stance, slightly guarded; reads as emotional numbness, pain, sadness; style: narration, monologue; good recording, quiet background; genuineness 0.0/6; vocal-burst blend 0.7/10; 16.6s, FRENCH.
12709_14178_000706 · in -28.6 dBFS · gain +8.7 dB · mls-00057
(contemplation, longing, sadness · narration, monologue)mais là sur cette goélette solitaire dans l'infini silence et le vide infini il n'eût pas été du métier celui qui aurait eu le cœur de rire pour nous en vérité nous n'y pensions guère j'étais très grave et s'il faut l'avouer un peu ému comme du reste chaque fois qu'il m'est arrivé d'officier de la sorte
full caption & clip details
A young adult feminine voice; delivery is normally alert, measured, slightly relaxed, steady; timbre is neutral-toned, neutral-bright, fairly smooth, balanced body; clear, no disfluency, fairly narrow pitch, light breath; affect is neutral, neutral stance, slightly guarded; reads as contemplation, longing, sadness; style: narration, monologue; good recording, no background noise; genuineness 0.0/6; vocal-burst blend 1.1/10; 18.7s, FRENCH.
12709_14178_000026 · in -28.2 dBFS · gain +8.2 dB · mls-00056
Shame ↓ / Emotional Numbness ↑c-mls-AB2 · #7
This chain comes from the two-sided rule: it only counts if both emotions move — Shame down and Emotional Numbness up — by at least 0.25 each.
The chain starts with Emotional Numbness clearly present — 0.62, higher than 62 % of clips in this corpus — and ends with it at the very top of the corpus at 0.98, higher than 98 % of clips in this corpus. That is a total rise of 0.36.
At the same time Shame goes the other way, from 0.99 (higher than 99 % of clips in this corpus) to 0.70 (higher than 70 % of clips in this corpus), a change of -0.29. Both halves had to happen for this chain to qualify.
It takes 5 clips to get there. Clip to clip the moves are +0.09, then +0.20, then -0.01, then +0.08 — not a clean run: step 3 moves back the other way by 0.01 before the chain recovers.
No single step is larger than the 0.25 cap, which is exactly what stops this being a jump cut: the change has to be spread across the clips instead of landing all at once.
Same speaker? The least similar clip scores 0.86 against the first clip, where 1.00 would mean an identical voice. That is above the 0.80 threshold the mining used — very likely one person. Neighbouring clips score at worst 0.85 against each other.
Voice consistency: these clips are separate recordings joined together, matching at 0.86. You may notice the voice shift a little between segments. Voice conversion has not been applied yet in this build. A planned pass will re-render every segment onto the first segment's voice, which removes this effect entirely.
Unchanged across all 5 clips: an elderly somewhat feminine voice · balanced body, slightly relaxed, clear, light breath
(shame, triumph, malevolence malice · measured, very low-energy, fairly steady, ASMR)comme je ne voulais point parler haut je fis quatre ou cinq pas en retour de ceux que j'avais faits en avant j'allongeai les mains j'appelai avec précaution adieu la compagnie ils m'avaient laissé tout seul
full caption & clip details
An elderly somewhat feminine voice; delivery is very low-energy, measured, slightly relaxed, fairly steady; timbre is slightly warm, slightly dark, slightly rough, balanced body; clear, little disfluency, fairly narrow pitch, light breath; affect is mildly positive, neutral stance, slightly guarded; reads as shame, triumph, malevolence malice; style: ASMR, whispered; average recording, no background noise; genuineness 1.1/6; vocal-burst blend 3.9/10; 12.7s, FRENCH.
3698_1902_000596 · in -28.1 dBFS · gain +8.1 dB · mls-00063
(fear, malevolence malice, anger· measured, normally alert, fairly steady, monologue)je pensai que n'étant pas bien loin de l'entrée je les rattraperais dedans ou dehors je marchai donc plus vite et avec plus d'assurance et repassai l'arcade par où j'étais entré pour regarder et chercher tout le long de la rouette aux anglais mais il était arrivé de mes camarades comme des sonneurs il semblait que la terre les eût dévorés
full caption & clip details
A young adult somewhat feminine voice; delivery is normally alert, measured, slightly relaxed, fairly steady; timbre is neutral-toned, neutral-bright, fairly smooth, balanced body; clear, no disfluency, fairly narrow pitch, light breath; affect is mildly negative, neutral stance, slightly guarded; reads as fear, malevolence malice, anger; style: monologue, narration; good recording, no background noise; genuineness 0.0/6; vocal-burst blend 3.5/10; 20.0s, FRENCH.
3698_1902_000235 · in -28.0 dBFS · gain +8.0 dB · mls-00063
(shame, fear, malevolence malice ·normal-paced, normally alert, fairly steady, monologue)j'eus comme un moment de malefièvre en songeant qu'il me fallait tout abandonner ou rentrer dans ces maudites cavernes et m'y trouver tout seul aux prises avec les embûches et les frayeurs qui y attendaient joseph
full caption & clip details
A young adult feminine voice; delivery is normally alert, normal-paced, slightly relaxed, fairly steady; timbre is neutral-toned, neutral-bright, fairly smooth, balanced body; clear, no disfluency, moderate pitch range, light breath; affect is mildly positive, neutral stance, slightly guarded; reads as shame, fear, malevolence malice; style: monologue, narration; good recording, no background noise; mildly explicit content; genuineness 0.2/6; vocal-burst blend 0.7/10; 11.5s, FRENCH.
3698_1902_000244 · in -27.0 dBFS · gain +7.0 dB · mls-00063
(fear, contemplation, longing·measured, subdued, steady, monologue)mais je me demandai si dans le cas où il ne s'agirait que de lui je me retirerais tranquillement de son danger mon âme de chrétien m'ayant répondu que non je demandai à mon coeur si l'amour de thérence n'était pas aussi solide en lui que l'amour du prochain dans ma conscience
full caption & clip details
A middle-aged somewhat feminine voice; delivery is subdued, measured, slightly relaxed, steady; timbre is neutral-toned, neutral-bright, fairly smooth, balanced body; clear, no disfluency, fairly narrow pitch, light breath; affect is mildly negative, neutral stance, slightly guarded; reads as fear, contemplation, longing; style: monologue, whispered; average recording, no background noise; genuineness 0.4/6; vocal-burst blend 2.3/10; 16.0s, FRENCH.
3698_1902_000839 · in -26.8 dBFS · gain +6.8 dB · mls-00063
(emotional numbness, awe, contemplation · measured, very low-energy, fairly steady, monologue)et la réponse que j'en reçus me fit repasser l'arcade noire et vaseuse bien résolûment et courir dans le souterrain non pas aussi gai mais aussi prompt que si c'eût été à ma propre noce
full caption & clip details
A young adult somewhat feminine voice; delivery is very low-energy, measured, slightly relaxed, fairly steady; timbre is neutral-toned, neutral-bright, fairly smooth, balanced body; clear, no disfluency, moderate pitch range, light breath; affect is mildly positive, neutral stance, slightly guarded; reads as emotional numbness, awe, contemplation; style: monologue, storytelling; good recording, quiet background; genuineness 0.6/6; vocal-burst blend 2.6/10; 12.2s, FRENCH.
3698_1902_000130 · in -30.2 dBFS · gain +10.2 dB · mls-00063
Contempt ↓ / Relief ↑c-mls-AB2 · #8
This chain comes from the two-sided rule: it only counts if both emotions move — Contempt down and Relief up — by at least 0.25 each.
The chain starts with Relief clearly present — 0.68, higher than 68 % of clips in this corpus — and ends with it at the very top of the corpus at 0.98, higher than 98 % of clips in this corpus. That is a total rise of 0.30.
At the same time Contempt goes the other way, from 0.99 (higher than 99 % of clips in this corpus) to 0.72 (higher than 72 % of clips in this corpus), a change of -0.27. Both halves had to happen for this chain to qualify.
It takes 5 clips to get there. Clip to clip the moves are +0.03, then +0.13, then +0.10, then +0.04 — an uneven climb, but always in the same direction.
No single step is larger than the 0.25 cap, which is exactly what stops this being a jump cut: the change has to be spread across the clips instead of landing all at once.
Same speaker? The least similar clip scores 0.94 against the first clip, where 1.00 would mean an identical voice. That is a strong match — almost certainly one person throughout. Neighbouring clips score at worst 0.92 against each other.
Voice consistency: these clips are separate recordings joined together. The measured match is tight (0.94), so any shift should be subtle — but you may still notice the voice change slightly from segment to segment. Voice conversion has not been applied yet in this build. A planned pass will re-render every segment onto the first segment's voice, which removes this effect entirely.
Unchanged across all 5 clips: a young adult feminine voice · neutral-toned, neutral-bright, fairly smooth, balanced body, quiet background, normal-paced, normally alert, slightly relaxed
(contempt, disgust, malevolence malice · almost no disfluency, moderate pitch range, formal, monologue)unter diesen verschiedenen gesträuchen die so groß sind wie die bäume der gemäßigten zone und unter ihrem feuchten schatten befanden sich massenweis wahre gebüsche lebendiger pflanzen hecken von pflanzenthieren und was die täuschung vollends beförderte
full caption & clip details
A young adult feminine voice; delivery is normally alert, normal-paced, slightly relaxed, fairly steady; timbre is neutral-toned, neutral-bright, fairly smooth, balanced body; clear, almost no disfluency, moderate pitch range, light breath; affect is neutral, neutral stance, slightly guarded; reads as contempt, disgust, malevolence malice; style: formal, monologue; average recording, quiet background; genuineness 0.0/6; vocal-burst blend 0.0/10; 14.3s, GERMAN.
3731_1614_000036 · in -27.7 dBFS · gain +7.7 dB · mls-00017
(jealousy and envy, anger, teasing· almost no disfluency, moderate pitch range, formal, narration)die mückenfische flogen von zweig zu zweig gleich einem schwarm colibris während andere gleich einem trupp becassinen unter unseren schritten aufzufliegen schienen gegen ein uhr gab der kapitän nemo das zeichen zum halt ich meines theils war wohl zufrieden damit und wir streckten uns nieder
full caption & clip details
A child feminine voice; delivery is normally alert, normal-paced, slightly relaxed, fairly steady; timbre is neutral-toned, neutral-bright, fairly smooth, balanced body; clear, almost no disfluency, moderate pitch range, light breath; affect is neutral, neutral stance, slightly guarded; reads as jealousy and envy, anger, teasing; style: formal, narration; average recording, quiet background; genuineness 0.0/6; vocal-burst blend 0.0/10; 17.8s, GERMAN.
3731_1614_000019 · in -29.2 dBFS · gain +9.2 dB · mls-00017
(contempt, malevolence malice, emotional numbness· almost no disfluency, moderate pitch range, formal, narration)dieses ausruhen schien mir köstlich nur mangelte uns die unterhaltung denn das anreden war so unmöglich als das erwidern ich näherte nur meinen dicken kupferkopf dem conseil's ich sah bei diesem wackern jungen die augen vor befriedigung glänzen und um es kund zu geben machte er in seiner schale höchst komische bewegungen
full caption & clip details
A child feminine voice; delivery is normally alert, normal-paced, slightly relaxed, fairly steady; timbre is neutral-toned, neutral-bright, fairly smooth, balanced body; clear, almost no disfluency, moderate pitch range, light breath; affect is neutral, neutral stance, slightly guarded; reads as contempt, malevolence malice, emotional numbness; style: formal, narration; good recording, quiet background; genuineness 0.0/6; vocal-burst blend 0.0/10; 18.8s, GERMAN.
3731_1614_000035 · in -26.3 dBFS · gain +6.3 dB · mls-00017
(fear, infatuation, awe· almost no disfluency, moderate pitch range, narration, formal)nach einem vierstündigen spaziergang war ich sehr erstaunt daß ich nicht heftigen hunger empfand woher diese stimmung des magens kam konnte ich nicht sagen dagegen spürte ich eine unüberwindliche neigung zum schlafen wie das bei allen tauchern der fall ist daher schlossen sich auch alsbald meine augen hinter ihrem dichten glas
full caption & clip details
A child feminine voice; delivery is normally alert, normal-paced, slightly relaxed, fairly steady; timbre is neutral-toned, neutral-bright, fairly smooth, balanced body; clear, almost no disfluency, moderate pitch range, light breath; affect is neutral, neutral stance, slightly guarded; reads as fear, infatuation, awe; style: narration, formal; good recording, quiet background; genuineness 0.5/6; vocal-burst blend 0.0/10; 18.4s, GERMAN.
3731_1614_000084 · in -27.4 dBFS · gain +7.4 dB · mls-00017
(relief, fear, triumph·no disfluency, fairly narrow pitch, formal, whispered)und ich sank in eine unwiderstehliche schlaftrunkenheit welche bisher nur durch die bewegung des gehens zu bekämpfen möglich war der kapitän nemo nebst seinem kräftigen genossen gaben uns hingestreckt im klaren wasser das beispiel zum schlafen
full caption & clip details
A young adult feminine voice; delivery is normally alert, normal-paced, slightly relaxed, fairly steady; timbre is neutral-toned, neutral-bright, fairly smooth, balanced body; clear, no disfluency, fairly narrow pitch, light breath; affect is neutral, neutral stance, slightly guarded; reads as relief, fear, triumph; style: formal, whispered; average recording, quiet background; genuineness 0.0/6; vocal-burst blend 0.0/10; 14.2s, GERMAN.
3731_1614_000049 · in -28.2 dBFS · gain +8.2 dB · mls-00017
Longing ↓ / Relief ↑c-mls-AB2 · #9
This chain comes from the two-sided rule: it only counts if both emotions move — Longing down and Relief up — by at least 0.25 each.
The chain starts with Relief clearly present — 0.63, higher than 63 % of clips in this corpus — and ends with it at the very top of the corpus at 0.99, higher than 99 % of clips in this corpus. That is a total rise of 0.36.
At the same time Longing goes the other way, from 0.96 (higher than 96 % of clips in this corpus) to 0.64 (higher than 64 % of clips in this corpus), a change of -0.33. Both halves had to happen for this chain to qualify.
It takes 5 clips to get there. Clip to clip the moves are +0.08, then +0.02, then +0.04, then +0.22 — a slow start, with most of the change arriving in the final step.
No single step is larger than the 0.25 cap, which is exactly what stops this being a jump cut: the change has to be spread across the clips instead of landing all at once.
Same speaker? The least similar clip scores 0.96 against the first clip, where 1.00 would mean an identical voice. That is a strong match — almost certainly one person throughout. Neighbouring clips score at worst 0.96 against each other.
Voice consistency: these clips are separate recordings joined together. The measured match is tight (0.96), so any shift should be subtle — but you may still notice the voice change slightly from segment to segment. Voice conversion has not been applied yet in this build. A planned pass will re-render every segment onto the first segment's voice, which removes this effect entirely.
Unchanged across all 5 clips: an elderly somewhat feminine voice · neutral-toned, fairly smooth, average recording, quiet background, slightly relaxed, clear, light breath
(longing, contemplation, sourness · measured, very low-energy, fairly steady, whispered)ook wil ik u wel bekennen ging zij voort op vertrouwelijken toon dat ik er wel eens over gedacht heb om ze bij een lombard te beleenen maar neen neen dat moet niet zijn de gravin van solms moet niet in woekeraars handen vallen
full caption & clip details
An elderly somewhat feminine voice; delivery is very low-energy, measured, slightly relaxed, fairly steady; timbre is neutral-toned, slightly dark, fairly smooth, balanced body; clear, frequent disfluency, moderate pitch range, light breath; affect is mildly positive, neutral stance, neutral openness; reads as longing, contemplation, sourness; style: whispered, monologue; average recording, quiet background; genuineness 3.0/6; vocal-burst blend 0.9/10; 14.2s, DUTCH.
1724_2757_000973 · in -23.4 dBFS · gain +3.4 dB · mls-00104
(contempt, longing, malevolence malice· measured, very low-energy, fairly steady, narration)hij zweeg en scheen zich even te bedenken zoo uwe genade nog niet besluiten kan zich van enkelen te ontdoen maar ze alleen tijdelijk wil afstaan weet ik een juwelier een eerlijk en discreet man die zulke zaken op hunne rechte waarde zal schatten
full caption & clip details
An elderly feminine voice; delivery is very low-energy, measured, slightly relaxed, fairly steady; timbre is neutral-toned, neutral-bright, fairly smooth, balanced body; clear, no disfluency, fairly narrow pitch, light breath; affect is mildly positive, neutral stance, neutral openness; reads as contempt, longing, malevolence malice; style: narration, whispered; average recording, quiet background; genuineness 1.2/6; vocal-burst blend 0.4/10; 15.1s, DUTCH.
1724_2757_002127 · in -24.8 dBFS · gain +4.8 dB · mls-00104
(longing, contemplation, fear· measured, normally alert, steady, monologue)vertrouw aan mij wat gij meent te konnen missen ben ik eerst onderricht hoeveel dat te zamen uitmaakt dan is mijn broeder de schepen dirk jansz graswinckel de man die u daarop de verlangde som zal voorschieten zonder interest
full caption & clip details
A young adult feminine voice; delivery is normally alert, measured, slightly relaxed, steady; timbre is neutral-toned, neutral-bright, fairly smooth, balanced body; clear, no disfluency, fairly narrow pitch, light breath; affect is neutral, neutral stance, slightly guarded; reads as longing, contemplation, fear; style: monologue, narration; average recording, quiet background; genuineness 0.8/6; vocal-burst blend 0.0/10; 12.5s, DUTCH.
1724_2757_000108 · in -24.7 dBFS · gain +4.7 dB · mls-00104
(anger, contemplation ·normal-paced, normally alert, fairly steady, narration)hij is met den handel rijk geworden heeft geene kinderen en is steeds geneigd op mijne voorspraak iemand in stilte te verplichten maar hij verlangt zeker onderpand voor de teruggave zij die op langen tijd uitgesteld en in dat zwak moeten wij hem met uw goedvinden te gemoet komen kan uwe genade in dit voorstel treden
full caption & clip details
A middle-aged feminine voice; delivery is normally alert, normal-paced, slightly relaxed, fairly steady; timbre is neutral-toned, neutral-bright, fairly smooth, balanced body; clear, no disfluency, moderate pitch range, light breath; affect is neutral, neutral stance, slightly guarded; reads as anger, contemplation; style: narration, whispered; average recording, quiet background; genuineness 0.9/6; vocal-burst blend 0.0/10; 17.9s, DUTCH.
1724_2757_002562 · in -24.7 dBFS · gain +4.7 dB · mls-00104
(relief, sourness, thankfulness gratitude·measured, very low-energy, fairly steady, whispered)ik zou u als mijn reddenden engel beschouwen zoo gij dit voor mij kondet verkrijgen ik wenschte u de helpende hand toe te reiken voor beter dan dit wellieve vrouwe doch in de moeielijkheid van t oogenblik moet nu allereerst worden voorzien
full caption & clip details
A middle-aged somewhat feminine voice; delivery is very low-energy, measured, slightly relaxed, fairly steady; timbre is neutral-toned, slightly dark, fairly smooth, slightly thin; clear, some disfluency, moderate pitch range, light breath; affect is mildly negative, neutral stance, neutral openness; reads as relief, sourness, thankfulness gratitude; style: whispered, narration; average recording, quiet background; genuineness 2.7/6; vocal-burst blend 0.9/10; 14.2s, DUTCH.
1724_2757_000262 · in -24.7 dBFS · gain +4.7 dB · mls-00104
Sourness ↓ / Concentration ↑c-mls-AB2 · #10
This chain comes from the two-sided rule: it only counts if both emotions move — Sourness down and Concentration up — by at least 0.25 each.
The chain starts with Concentration around average — 0.57, higher than 57 % of clips in this corpus — and ends with it at the very top of the corpus at 0.93, higher than 93 % of clips in this corpus. That is a total rise of 0.36.
At the same time Sourness goes the other way, from 0.98 (higher than 98 % of clips in this corpus) to 0.72 (higher than 72 % of clips in this corpus), a change of -0.26. Both halves had to happen for this chain to qualify.
It takes 3 clips to get there. Clip to clip the moves are +0.12, then +0.24 — a fairly even climb, though some clips carry more of the change than others.
No single step is larger than the 0.25 cap, which is exactly what stops this being a jump cut: the change has to be spread across the clips instead of landing all at once.
Same speaker? The least similar clip scores 0.92 against the first clip, where 1.00 would mean an identical voice. That is a strong match — almost certainly one person throughout. Neighbouring clips score at worst 0.93 against each other.
Voice consistency: these clips are separate recordings joined together. The measured match is tight (0.92), so any shift should be subtle — but you may still notice the voice change slightly from segment to segment. Voice conversion has not been applied yet in this build. A planned pass will re-render every segment onto the first segment's voice, which removes this effect entirely.
Unchanged across all 3 clips: an adult masculine voice · neutral-toned, balanced body, average recording, quiet background, normally alert, slightly relaxed, fairly steady, light breath
(sourness, contentment, jealousy and envy · measured, some disfluency, average clarity, didactic)meno grave all'aspetto più elegante nel portamento ma pur sempre severo e rispondente a quell'immagine di dignità e di forza che non dovrebbe scompagnarsi mai dall'idea dell'uomo
full caption & clip details
An adult masculine voice; delivery is normally alert, measured, slightly relaxed, fairly steady; timbre is neutral-toned, slightly dark, slightly rough, balanced body; average clarity, some disfluency, moderate pitch range, light breath; affect is neutral, neutral stance, slightly guarded; reads as sourness, contentment, jealousy and envy; style: didactic, monologue; average recording, quiet background; genuineness 3.9/6; vocal-burst blend 3.4/10; 11.7s, ITALIAN.
10446_10415_000708 · in -25.8 dBFS · gain +5.8 dB · mls-00065
(contentment, affection, pride·normal-paced, some disfluency, average clarity, monologue)egli frattanto non vedeva più il monachino ma una bella e graziosa fanciulla l'aria birichina dello scolaro in vacanze non c'era più ma l'aspetto della donna che sente e che pensa rendeva il suo volto anche più attraente che non fosse da prima
full caption & clip details
An adult masculine voice; delivery is normally alert, normal-paced, slightly relaxed, fairly steady; timbre is neutral-toned, neutral-bright, fairly smooth, balanced body; average clarity, some disfluency, moderate pitch range, light breath; affect is neutral, neutral stance, slightly guarded; reads as contentment, affection, pride; style: monologue, authoritative; average recording, quiet background; genuineness 1.4/6; vocal-burst blend 1.0/10; 14.5s, ITALIAN.
10446_10415_001555 · in -26.0 dBFS · gain +6.0 dB · mls-00066
(concentration·measured, frequent disfluency, somewhat unclear, monologue)come balbettò ella avvicinandosi signorina eccomi qua rispose egli dissimulando con un profondo inchino la sua profonda commozione seguì una scena muta di forse un minuto il solito minuto che parve un secolo
full caption & clip details
An adult masculine voice; delivery is normally alert, measured, slightly relaxed, fairly steady; timbre is neutral-toned, slightly dark, fairly smooth, balanced body; somewhat unclear, frequent disfluency, fairly narrow pitch, light breath; affect is neutral, neutral stance, slightly guarded; reads as concentration; style: monologue, didactic; average recording, quiet background; genuineness 3.2/6; vocal-burst blend 1.6/10; 14.7s, ITALIAN.
10446_10415_001216 · in -25.9 dBFS · gain +5.9 dB · mls-00066
Thankfulness Gratitude ↓ / Shame ↑c-mls-AB2 · #11
This chain comes from the two-sided rule: it only counts if both emotions move — Thankfulness Gratitude down and Shame up — by at least 0.25 each.
The chain starts with Shame clearly present — 0.68, higher than 68 % of clips in this corpus — and ends with it at the very top of the corpus at 1.00, virtually no clip in this corpus scores higher. That is a total rise of 0.31.
At the same time Thankfulness Gratitude goes the other way, from 0.99 (higher than 99 % of clips in this corpus) to 0.72 (higher than 72 % of clips in this corpus), a change of -0.26. Both halves had to happen for this chain to qualify.
It takes 4 clips to get there. Clip to clip the moves are +0.20, then +0.03, then +0.09 — most of the change happening immediately, then levelling off.
No single step is larger than the 0.25 cap, which is exactly what stops this being a jump cut: the change has to be spread across the clips instead of landing all at once.
Same speaker? The least similar clip scores 0.91 against the first clip, where 1.00 would mean an identical voice. That is a strong match — almost certainly one person throughout. Neighbouring clips score at worst 0.94 against each other.
Voice consistency: these clips are separate recordings joined together. The measured match is tight (0.91), so any shift should be subtle — but you may still notice the voice change slightly from segment to segment. Voice conversion has not been applied yet in this build. A planned pass will re-render every segment onto the first segment's voice, which removes this effect entirely.
Unchanged across all 4 clips: a child masculine voice · neutral-toned, neutral-bright, fairly smooth, balanced body, quiet background, normal-paced, normally alert, slightly relaxed
(thankfulness gratitude, infatuation, contentment · no disfluency, average clarity, narration, monologue)tu opowiada ący uśmiechnął się z gorzką ironią gdybym miał żonę zbytnicę i trzech synów utrac uszów nie wiem czy by mię tyle kosztowali co ten eden człowiek
full caption & clip details
A child masculine voice; delivery is normally alert, normal-paced, slightly relaxed, fairly steady; timbre is neutral-toned, neutral-bright, fairly smooth, balanced body; average clarity, no disfluency, moderate pitch range, light breath; affect is neutral, neutral stance, slightly guarded; reads as thankfulness gratitude, infatuation, contentment; style: narration, monologue; good recording, quiet background; genuineness 0.3/6; vocal-burst blend 0.0/10; 10.3s, POLISH.
6892_10462_000754 · in -23.0 dBFS · gain +3.0 dB · mls-00106
(contentment, infatuation, affection·some disfluency, average clarity, narration, monologue)na cóż on tak wydawał zawołałyśmy obie narkotyki pieniądz bóg raczy wiedzieć na co zawsze mówił że mu potrzeba ogromnych sum na doświadczenia naukowe i rzeczywiście prowadził e z wielkim nakładem ale co eszcze nierównie więce pochłaniało to ego codzienne niewyczerpane fantaz
full caption & clip details
A child masculine voice; delivery is normally alert, normal-paced, slightly relaxed, fairly steady; timbre is neutral-toned, neutral-bright, fairly smooth, balanced body; average clarity, some disfluency, moderate pitch range, light breath; affect is neutral, neutral stance, slightly guarded; reads as contentment, infatuation, affection; style: narration, monologue; good recording, quiet background; genuineness 0.7/6; vocal-burst blend 3.8/10; 17.1s, POLISH.
6892_10462_000999 · in -23.2 dBFS · gain +3.2 dB · mls-00106
(contemplation, sexual lust, shame· some disfluency, average clarity, narration, storytelling)i tak na przykład na droższe tytunie nazywał mdłą trawą emu potrzebny był haszysz ów narkotyk indy ski którego tak trudno u nas dostać a ednak musiałem go ciągle sprowadzać za ba eczne sumy bo kilka dni przebytych bez haszyszu wtrącało go w ponurość i
full caption & clip details
A child masculine voice; delivery is normally alert, normal-paced, slightly relaxed, fairly steady; timbre is neutral-toned, neutral-bright, fairly smooth, balanced body; average clarity, some disfluency, moderate pitch range, light breath; affect is neutral, neutral stance, slightly guarded; reads as contemplation, sexual lust, shame; style: narration, storytelling; average recording, quiet background; genuineness 0.4/6; vocal-burst blend 1.9/10; 18.1s, POLISH.
6892_10462_001019 · in -23.9 dBFS · gain +3.9 dB · mls-00106
(shame, pain, contemplation · some disfluency, clear, narration, storytelling)takich niebezpiecznych nawyknień miał mnóstwo w każdym kra u uczył się nowych a zwiedziliśmy kra ów niemało namówił mię na podróże na które chętnie przystałem bo mo e rodzinne strony obrzydły mi po kilku latach dla nieustannych dokuczań akich doznawałem od obrażonych kuzynów i całe rodziny
full caption & clip details
A child masculine voice; delivery is normally alert, normal-paced, slightly relaxed, fairly steady; timbre is neutral-toned, neutral-bright, fairly smooth, balanced body; clear, some disfluency, moderate pitch range, light breath; affect is neutral, neutral stance, slightly guarded; reads as shame, pain, contemplation; style: narration, storytelling; average recording, quiet background; genuineness 1.3/6; vocal-burst blend 3.4/10; 19.2s, POLISH.
6892_10462_000679 · in -23.0 dBFS · gain +3.0 dB · mls-00106
This chain comes from the two-sided rule: it only counts if both emotions move — Emotional Numbness down and Bitterness up — by at least 0.25 each.
The chain starts with Bitterness clearly present — 0.65, higher than 65 % of clips in this corpus — and ends with it at the very top of the corpus at 0.95, higher than 95 % of clips in this corpus. That is a total rise of 0.30.
At the same time Emotional Numbness goes the other way, from 0.98 (higher than 98 % of clips in this corpus) to 0.69 (higher than 69 % of clips in this corpus), a change of -0.29. Both halves had to happen for this chain to qualify.
It takes 4 clips to get there. Clip to clip the moves are +0.20, then -0.06, then +0.16 — not a clean run: step 2 moves back the other way by 0.06 before the chain recovers.
No single step is larger than the 0.25 cap, which is exactly what stops this being a jump cut: the change has to be spread across the clips instead of landing all at once.
Same speaker? The least similar clip scores 0.95 against the first clip, where 1.00 would mean an identical voice. That is a strong match — almost certainly one person throughout. Neighbouring clips score at worst 0.95 against each other.
Voice consistency: these clips are separate recordings joined together. The measured match is tight (0.95), so any shift should be subtle — but you may still notice the voice change slightly from segment to segment. Voice conversion has not been applied yet in this build. A planned pass will re-render every segment onto the first segment's voice, which removes this effect entirely.
Unchanged across all 4 clips: a middle-aged masculine voice · neutral-toned, neutral-bright, fairly smooth, balanced body, average recording, normally alert, slightly relaxed, fairly steady
(emotional numbness, sadness, relief · measured, almost no disfluency, monologue, narration)denn obzwar er viel von dem prediger beschworen wurde auch männiglich in der kirche auf die kniee gefallen und fleißig und andächtig gebetet so hat er doch mit dem austreiben nichts als spott und kurzweil getrieben
full caption & clip details
A middle-aged masculine voice; delivery is normally alert, measured, slightly relaxed, fairly steady; timbre is neutral-toned, neutral-bright, fairly smooth, balanced body; average clarity, almost no disfluency, moderate pitch range, light breath; affect is neutral, neutral stance, slightly guarded; reads as emotional numbness, sadness, relief; style: monologue, narration; average recording, no background noise; genuineness 0.2/6; vocal-burst blend 0.0/10; 14.6s, GERMAN.
11927_12408_001302 · in -29.2 dBFS · gain +9.2 dB · mls-00011
(relief, sadness, jealousy and envy· measured, some disfluency, monologue, narration)so hat er oft gesagt ja er wolle weichen er müsse auch wohl räumen aber er hat allerlei gefordert ihm zu erlauben daß er es mitnehmen dürfe wann ihm dann nun das eine abgeschlagen wurde so hatte er gleich das andere bei der hand
full caption & clip details
A middle-aged masculine voice; delivery is normally alert, measured, slightly relaxed, fairly steady; timbre is neutral-toned, neutral-bright, fairly smooth, balanced body; average clarity, some disfluency, moderate pitch range, light breath; affect is neutral, neutral stance, slightly guarded; reads as relief, sadness, jealousy and envy; style: monologue, narration; average recording, quiet background; genuineness 1.2/6; vocal-burst blend 0.0/10; 16.4s, GERMAN.
11927_12408_000412 · in -26.7 dBFS · gain +6.7 dB · mls-00010
(pride, relief, malevolence malice·slow, frequent disfluency, monologue, narration)es stand einer in der kirchen der den hut aufbehalten hatte da forderte er von dem prediger daß er den hut dem menschen vom kopfe nehmen und mit sich führen dürfe
full caption & clip details
A child masculine voice; delivery is normally alert, slow, slightly relaxed, fairly steady; timbre is neutral-toned, neutral-bright, fairly smooth, balanced body; average clarity, frequent disfluency, moderate pitch range, light breath; affect is neutral, neutral stance, slightly guarded; reads as pride, relief, malevolence malice; style: monologue, narration; average recording, quiet background; genuineness 0.6/6; vocal-burst blend 0.0/10; 11.8s, GERMAN.
11927_12408_001071 · in -27.1 dBFS · gain +7.1 dB · mls-00010
(bitterness, distress, longing·measured, almost no disfluency, didactic, monologue)aber der prediger trug mit recht sorge wenn er ihm den hut gestattet so hätten mit dem hute auch haut und haar davongehen müssen letztlich aber als er vermerkte daß seine zeit verflossen
full caption & clip details
A middle-aged masculine voice; delivery is normally alert, measured, slightly relaxed, fairly steady; timbre is neutral-toned, neutral-bright, fairly smooth, balanced body; average clarity, almost no disfluency, moderate pitch range, light breath; affect is neutral, neutral stance, slightly guarded; reads as bitterness, distress, longing; style: didactic, monologue; average recording, quiet background; genuineness 0.7/6; vocal-burst blend 0.0/10; 12.7s, GERMAN.
11927_12408_001540 · in -27.3 dBFS · gain +7.3 dB · mls-00011
Fear ↓ / Jealousy and Envy ↑c-mls-AB2 · #13
This chain comes from the two-sided rule: it only counts if both emotions move — Fear down and Jealousy and Envy up — by at least 0.25 each.
The chain starts with Jealousy and Envy clearly present — 0.69, higher than 69 % of clips in this corpus — and ends with it at the very top of the corpus at 0.97, higher than 97 % of clips in this corpus. That is a total rise of 0.28.
At the same time Fear goes the other way, from 0.98 (higher than 98 % of clips in this corpus) to 0.69 (higher than 69 % of clips in this corpus), a change of -0.29. Both halves had to happen for this chain to qualify.
It takes 3 clips to get there. Clip to clip the moves are +0.21, then +0.07 — most of the change happening immediately, then levelling off.
No single step is larger than the 0.25 cap, which is exactly what stops this being a jump cut: the change has to be spread across the clips instead of landing all at once.
Same speaker? The least similar clip scores 0.91 against the first clip, where 1.00 would mean an identical voice. That is a strong match — almost certainly one person throughout. Neighbouring clips score at worst 0.93 against each other.
Voice consistency: these clips are separate recordings joined together. The measured match is tight (0.91), so any shift should be subtle — but you may still notice the voice change slightly from segment to segment. Voice conversion has not been applied yet in this build. A planned pass will re-render every segment onto the first segment's voice, which removes this effect entirely.
Unchanged across all 3 clips: a middle-aged masculine voice · neutral-toned, neutral-bright, balanced body, no background noise, subdued, slightly relaxed, almost no disfluency, clear
(malevolence malice, fear, sadness · slow, steady, fairly narrow pitch, narration)und der alte schwarzkünstler schien dem nichts troz bieten zu wollen so sah er aus als er den teufel bannte sagte die wahrsagerin
full caption & clip details
A middle-aged masculine voice; delivery is subdued, slow, slightly relaxed, steady; timbre is neutral-toned, neutral-bright, fairly smooth, balanced body; clear, almost no disfluency, fairly narrow pitch, light breath; affect is neutral, neutral stance, slightly guarded; reads as malevolence malice, fear, sadness; style: narration, monologue; good recording, no background noise; genuineness 0.3/6; vocal-burst blend 0.6/10; 11.5s, GERMAN.
252_1552_000553 · in -24.4 dBFS · gain +4.4 dB · mls-00016
(malevolence malice, bitterness, contempt· slow, fairly steady, fairly narrow pitch, storytelling)nur haben sie ihm nachher die hände gefaltet daß er hier unten wider willen beten muß und warum betet er denn fragte ich zornig da drüben über uns im himmelssee funkeln und schwimmen zwar unzählige sterne
full caption & clip details
A middle-aged masculine voice; delivery is subdued, slow, slightly relaxed, fairly steady; timbre is neutral-toned, neutral-bright, rough, balanced body; clear, almost no disfluency, fairly narrow pitch, audible breath; affect is neutral, neutral stance, slightly guarded; reads as malevolence malice, bitterness, contempt; style: storytelling, narration; average recording, no background noise; genuineness 0.6/6; vocal-burst blend 0.1/10; 15.4s, GERMAN.
252_1552_000588 · in -21.0 dBFS · gain +1.0 dB · mls-00016
(jealousy and envy, pride, contempt ·measured, fairly steady, moderate pitch range, storytelling)aber wenn es welten sind wie viele kluge köpfe behaupten so giebt es auch schädel auf ihnen und würmer wie hier unten das geht so fort durch die ganze unermeßlichkeit und der baseler todtentanz wird dadurch nur um so lustiger und wilder und der ballsaal größer
full caption & clip details
A middle-aged masculine voice; delivery is subdued, measured, slightly relaxed, fairly steady; timbre is neutral-toned, neutral-bright, slightly rough, balanced body; clear, almost no disfluency, moderate pitch range, light breath; affect is neutral, neutral stance, slightly guarded; reads as jealousy and envy, pride, contempt; style: storytelling, monologue; average recording, no background noise; genuineness 0.6/6; vocal-burst blend 0.0/10; 18.0s, GERMAN.
252_1552_000213 · in -21.2 dBFS · gain +1.2 dB · mls-00016
Shame ↓ / Emotional Numbness ↑c-mls-AB2 · #14
This chain comes from the two-sided rule: it only counts if both emotions move — Shame down and Emotional Numbness up — by at least 0.25 each.
The chain starts with Emotional Numbness clearly present — 0.59, higher than 59 % of clips in this corpus — and ends with it strongly present at 0.88, higher than 88 % of clips in this corpus. That is a total rise of 0.29.
At the same time Shame goes the other way, from 0.97 (higher than 97 % of clips in this corpus) to 0.70 (higher than 70 % of clips in this corpus), a change of -0.27. Both halves had to happen for this chain to qualify.
It takes 3 clips to get there. Clip to clip the moves are +0.09, then +0.19 — a fairly even climb, though some clips carry more of the change than others.
No single step is larger than the 0.25 cap, which is exactly what stops this being a jump cut: the change has to be spread across the clips instead of landing all at once.
Same speaker? The least similar clip scores 0.94 against the first clip, where 1.00 would mean an identical voice. That is a strong match — almost certainly one person throughout. Neighbouring clips score at worst 0.95 against each other.
Voice consistency: these clips are separate recordings joined together. The measured match is tight (0.94), so any shift should be subtle — but you may still notice the voice change slightly from segment to segment. Voice conversion has not been applied yet in this build. A planned pass will re-render every segment onto the first segment's voice, which removes this effect entirely.
Unchanged across all 3 clips: a young adult masculine voice · neutral-toned, neutral-bright, fairly smooth, balanced body, quiet background, normal-paced, normally alert, slightly relaxed
(shame, infatuation, longing · average clarity, narration, storytelling)pokoju widzenie znikło wokulski ocknął się był znowu tylko człowiekiem zbolałym i słabym ale w jego duszy huczał jakiś potężny głos niby echo kwietniowej burzy grzmotami zapowiadającej wiosnę i zmartwychwstanie
full caption & clip details
A young adult masculine voice; delivery is normally alert, normal-paced, slightly relaxed, fairly steady; timbre is neutral-toned, neutral-bright, fairly smooth, balanced body; average clarity, some disfluency, moderate pitch range, light breath; affect is neutral, neutral stance, slightly guarded; reads as shame, infatuation, longing; style: narration, storytelling; average recording, quiet background; genuineness 0.9/6; vocal-burst blend 1.8/10; 13.0s, POLISH.
6892_9500_000322 · in -25.1 dBFS · gain +5.1 dB · mls-00112
(shame, contentment, sadness·clear, narration, monologue)pierwszego czerwca odwiedził go szlangbaum wszedł zakłopotany ale przypatrzywszy się wokulskiemu nabrał otuchy nie odwiedzałem cię do tej pory zaczął bo wiem żeś był niezdrów i nie chciałeś nikogo widywać no ale dzięki bogu już wszystko przeszło
full caption & clip details
A young adult masculine voice; delivery is normally alert, normal-paced, slightly relaxed, fairly steady; timbre is neutral-toned, neutral-bright, fairly smooth, balanced body; clear, some disfluency, moderate pitch range, light breath; affect is neutral, neutral stance, slightly guarded; reads as shame, contentment, sadness; style: narration, monologue; average recording, quiet background; genuineness 0.3/6; vocal-burst blend 3.8/10; 15.1s, POLISH.
6892_9500_000116 · in -25.6 dBFS · gain +5.6 dB · mls-00112
(average clarity, monologue, narration)kręcił się na krześle i zpod oka rzucał spojrzenia na pokój może spodziewał się znaleść w nim więcej nieładu masz jaki interes zapytał go wokulski nie tyle interes ile propozycyą
full caption & clip details
A young adult masculine voice; delivery is normally alert, normal-paced, slightly relaxed, fairly steady; timbre is neutral-toned, neutral-bright, fairly smooth, balanced body; average clarity, some disfluency, moderate pitch range, light breath; affect is neutral, neutral stance, slightly guarded; no dominant emotion; style: monologue, narration; good recording, quiet background; genuineness 0.8/6; vocal-burst blend 2.1/10; 11.6s, POLISH.
6892_9500_000375 · in -25.9 dBFS · gain +5.9 dB · mls-00112
Emotional Numbness ↓ / Interest ↑c-mls-AB2 · #15
This chain comes from the two-sided rule: it only counts if both emotions move — Emotional Numbness down and Interest up — by at least 0.25 each.
The chain starts with Interest below average — 0.40, lower than 60 % of clips in this corpus — and ends with it at the very top of the corpus at 0.99, higher than 99 % of clips in this corpus. That is a total rise of 0.59.
At the same time Emotional Numbness goes the other way, from 0.95 (higher than 95 % of clips in this corpus) to 0.47 (lower than 53 % of clips in this corpus), a change of -0.48. Both halves had to happen for this chain to qualify.
It takes 4 clips to get there. Clip to clip the moves are +0.19, then +0.19, then +0.20 — an even, steady climb — each clip carries about the same share.
No single step is larger than the 0.25 cap, which is exactly what stops this being a jump cut: the change has to be spread across the clips instead of landing all at once.
Same speaker? The least similar clip scores 0.94 against the first clip, where 1.00 would mean an identical voice. That is a strong match — almost certainly one person throughout. Neighbouring clips score at worst 0.95 against each other.
Voice consistency: these clips are separate recordings joined together. The measured match is tight (0.94), so any shift should be subtle — but you may still notice the voice change slightly from segment to segment. Voice conversion has not been applied yet in this build. A planned pass will re-render every segment onto the first segment's voice, which removes this effect entirely.
Unchanged across all 4 clips: a child masculine voice · neutral-toned, neutral-bright, fairly smooth, balanced body, quiet background, normally alert, slightly relaxed, some disfluency
(emotional numbness, disgust · normal-paced, steady, average clarity, narration)gdzie ona się znalazła tam obok niej wszystko bladło inne kobiety były jej tłem a mężczyźni niewolnikami i to wszystko przeszło i dziś w tym salonie chłodno ciemno i pusto
full caption & clip details
A child masculine voice; delivery is normally alert, normal-paced, slightly relaxed, steady; timbre is neutral-toned, neutral-bright, fairly smooth, balanced body; average clarity, some disfluency, moderate pitch range, light breath; affect is neutral, neutral stance, slightly guarded; reads as emotional numbness, disgust; style: narration, monologue; good recording, quiet background; genuineness 0.1/6; vocal-burst blend 0.0/10; 12.3s, POLISH.
6892_8764_001950 · in -25.1 dBFS · gain +5.2 dB · mls-00111
(bitterness, triumph, pride·fast, fairly steady, slurred, monologue)jest tylko ona i niewidzialny pająk smutku który zawsze zasnuwa szarą siecią te miejsca gdzie byliśmy szczęśliwi i zkąd szczęście uciekło już uciekło panna izabela wyłamywała sobie palce ażeby pohamować się od łez których wstyd jej było nawet w pustce i w nocy
full caption & clip details
A young adult masculine voice; delivery is normally alert, fast, slightly relaxed, fairly steady; timbre is neutral-toned, neutral-bright, fairly smooth, balanced body; slurred, some disfluency, moderate pitch range, light breath; affect is neutral, neutral stance, slightly guarded; reads as bitterness, triumph, pride; style: monologue, narration; average recording, quiet background; genuineness 1.5/6; vocal-burst blend 5.2/10; 16.7s, POLISH.
6892_8764_000938 · in -25.5 dBFS · gain +5.5 dB · mls-00111
(pride, contemplation, sadness·normal-paced, fairly steady, average clarity, narration)wszyscy ją opuścili z wyjątkiem hrabiny karolowej która kiedy wezbrał jej zły humor przychodziła tu i szeroko zasiadłszy na kanapie prawiła wśród westchnień tak droga belciu musisz przyznać że popełniłaś kilka błędów nie
full caption & clip details
A child masculine voice; delivery is normally alert, normal-paced, slightly relaxed, fairly steady; timbre is neutral-toned, neutral-bright, fairly smooth, balanced body; average clarity, some disfluency, moderate pitch range, light breath; affect is neutral, neutral stance, slightly guarded; reads as pride, contemplation, sadness; style: narration, monologue; average recording, quiet background; genuineness 1.3/6; vocal-burst blend 4.2/10; 14.1s, POLISH.
6892_8764_001708 · in -24.4 dBFS · gain +4.4 dB · mls-00111
(interest, pride, bitterness· normal-paced, fairly steady, average clarity, monologue)nie mówię o wiktorze emanuelu bo tamto był przelotny kaprys króla trochę liberalnego i zresztą bardzo zadłużonego na takie stosunki trzeba mieć więcej nie powiem taktu ale doświadczenia ciagnęłaciągnęła hrabina skromnie spuszczając powieki ale wypuścić czy jeżeli chcesz odrzucić
full caption & clip details
A young adult masculine voice; delivery is normally alert, normal-paced, slightly relaxed, fairly steady; timbre is neutral-toned, neutral-bright, fairly smooth, balanced body; average clarity, some disfluency, moderate pitch range, light breath; affect is neutral, neutral stance, slightly guarded; reads as interest, pride, bitterness; style: monologue, storytelling; average recording, quiet background; genuineness 2.9/6; vocal-burst blend 6.9/10; 18.2s, POLISH.
6892_8764_000933 · in -24.6 dBFS · gain +4.6 dB · mls-00111
Affection ↓ / Triumph ↑c-mls-AB2 · #16
This chain comes from the two-sided rule: it only counts if both emotions move — Affection down and Triumph up — by at least 0.25 each.
The chain starts with Triumph around average — 0.51, higher than 51 % of clips in this corpus — and ends with it at the very top of the corpus at 0.99, higher than 99 % of clips in this corpus. That is a total rise of 0.47.
At the same time Affection goes the other way, from 0.99 (higher than 99 % of clips in this corpus) to 0.60 (higher than 60 % of clips in this corpus), a change of -0.40. Both halves had to happen for this chain to qualify.
It takes 3 clips to get there. Clip to clip the moves are +0.25, then +0.23 — an even, steady climb — each clip carries about the same share.
No single step is larger than the 0.25 cap, which is exactly what stops this being a jump cut: the change has to be spread across the clips instead of landing all at once.
Same speaker? The least similar clip scores 0.76 against the first clip, where 1.00 would mean an identical voice. That is below the 0.80 threshold the mining used — treat the “same speaker” claim here with caution. Neighbouring clips score at worst 0.76 against each other.
Voice consistency: these clips are separate recordings joined together and the match is loose (0.76, under the 0.80 threshold), so the voice may audibly change between segments. Voice conversion has not been applied yet in this build. A planned pass will re-render every segment onto the first segment's voice, which removes this effect entirely.
Unchanged across all 3 clips: an elderly somewhat masculine voice · neutral-toned, average recording
(affection, confusion, awe · slow, very low-energy, tense, dramatic)lei tu carlino lei tu ma come io oh dio ma che fui crudele lo riconosco
full caption & clip details
An elderly somewhat masculine voice; delivery is very low-energy, slow, tense, variable; timbre is neutral-toned, bright, gravelly, slightly thin; slurred, some disfluency, very wide pitch range, audible breath; affect is elated, very submissive, very vulnerable; reads as affection, confusion, awe; style: dramatic, casual; average recording, quiet background; genuineness 1.9/6; vocal-burst blend 4.6/10; 10.0s, ITALIAN.
4974_5568_000394 · in -27.8 dBFS · gain +7.8 dB · mls-00075
(shame, embarrassment, distress·measured, normally alert, slightly relaxed, monologue)e tanto più mi dolgo della mia crudeltà in quanto quel poverino dovette credere senza dubbio ch'io avessi voluto prendermi il gusto di smascherarlo di fronte al paese con quella burla
full caption & clip details
A young adult feminine voice; delivery is normally alert, measured, slightly relaxed, fairly steady; timbre is neutral-toned, neutral-bright, fairly smooth, slightly thin; average clarity, some disfluency, moderate pitch range, light breath; affect is neutral, neutral stance, slightly guarded; reads as shame, embarrassment, distress; style: monologue, narration; average recording, no background noise; genuineness 1.3/6; vocal-burst blend 3.3/10; 12.5s, ITALIAN.
4974_5568_000144 · in -31.4 dBFS · gain +11.4 dB · mls-00075
(triumph, shame, relief· measured, very low-energy, slightly relaxed, narration)mentre ero più che sicuro della sua buona fede più che sicuro ormai d'essere stato uno sciocco a maravigliarmi tanto poiché io stesso avevo già sperimentato
full caption & clip details
An elderly somewhat feminine voice; delivery is very low-energy, measured, slightly relaxed, fairly steady; timbre is neutral-toned, slightly dark, rough, thin; slurred, frequent disfluency, narrow pitch range, audible breath; affect is mildly negative, neutral stance, slightly guarded; reads as triumph, shame, relief; style: narration, whispered; average recording, quiet background; genuineness 1.6/6; vocal-burst blend 2.5/10; 13.7s, ITALIAN.
4974_5568_000049 · in -32.5 dBFS · gain +12.6 dB · mls-00075
Jealousy and Envy ↓ / Emotional Numbness ↑c-mls-AB2 · #17
This chain comes from the two-sided rule: it only counts if both emotions move — Jealousy and Envy down and Emotional Numbness up — by at least 0.25 each.
The chain starts with Emotional Numbness clearly present — 0.66, higher than 66 % of clips in this corpus — and ends with it at the very top of the corpus at 0.93, higher than 93 % of clips in this corpus. That is a total rise of 0.28.
At the same time Jealousy and Envy goes the other way, from 0.98 (higher than 98 % of clips in this corpus) to 0.73 (higher than 73 % of clips in this corpus), a change of -0.26. Both halves had to happen for this chain to qualify.
It takes 5 clips to get there. Clip to clip the moves are +0.00, then +0.12, then +0.00, then +0.16 — a slow start, with most of the change arriving in the final step.
No single step is larger than the 0.25 cap, which is exactly what stops this being a jump cut: the change has to be spread across the clips instead of landing all at once.
Same speaker? The least similar clip scores 0.88 against the first clip, where 1.00 would mean an identical voice. That is above the 0.80 threshold the mining used — very likely one person. Neighbouring clips score at worst 0.88 against each other.
Voice consistency: these clips are separate recordings joined together, matching at 0.88. You may notice the voice shift a little between segments. Voice conversion has not been applied yet in this build. A planned pass will re-render every segment onto the first segment's voice, which removes this effect entirely.
Unchanged across all 5 clips: a middle-aged masculine voice · neutral-toned, slightly dark, average recording, quiet background, measured, normally alert, slightly relaxed, fairly steady
(jealousy and envy, disgust, concentration · some disfluency, slurred, audible breath, narration)de heer boreel is oud en ziekelijk hervatte van espenblad zonder die loftuiting op zijn uitzicht te beantwoorden en de heer van beuningen is niet rekkelijk en volgzaam genoeg naar den zin van uwe regeering gronden te over waarop de heer de
full caption & clip details
A middle-aged masculine voice; delivery is normally alert, measured, slightly relaxed, fairly steady; timbre is neutral-toned, slightly dark, slightly rough, balanced body; slurred, some disfluency, fairly narrow pitch, audible breath; affect is neutral, neutral stance, slightly guarded; reads as jealousy and envy, disgust, concentration; style: narration, cartoonish; average recording, quiet background; genuineness 1.0/6; vocal-burst blend 2.3/10; 16.5s, DUTCH.
2450_10026_002346 · in -28.1 dBFS · gain +8.1 dB · mls-00084
(jealousy and envy, disgust, concentration · some disfluency, slurred, audible breath, narration)de heer boreel is oud en ziekelijk hervatte van espenblad zonder die loftuiting op zijn uitzicht te beantwoorden en de heer van beuningen is niet rekkelijk en volgzaam genoeg naar den zin van uwe regeering gronden te over waarop de heer de
full caption & clip details
A middle-aged masculine voice; delivery is normally alert, measured, slightly relaxed, fairly steady; timbre is neutral-toned, slightly dark, slightly rough, balanced body; slurred, some disfluency, fairly narrow pitch, audible breath; affect is neutral, neutral stance, slightly guarded; reads as jealousy and envy, disgust, concentration; style: narration, cartoonish; average recording, quiet background; genuineness 1.0/6; vocal-burst blend 2.3/10; 16.5s, DUTCH.
2450_10026_002346 · in -28.1 dBFS · gain +8.1 dB · mls-00084
(anger, contempt, concentration ·frequent disfluency, somewhat unclear, audible breath, cartoonish)onder s hands aan de witt zoû kunnen te kennen geven dat een ander ambassadeur niet onwelkom zoû wezen aan het fransche hof wees overtuigd zeide d'estrades dat de heer de lionne zoowel als de koning mijn meester volkomen bekend zijn met de schatting waarin ik u houde
full caption & clip details
A middle-aged masculine voice; delivery is normally alert, measured, slightly relaxed, fairly steady; timbre is neutral-toned, slightly dark, rough, thin; somewhat unclear, frequent disfluency, fairly narrow pitch, audible breath; affect is neutral, slightly dominant, fairly guarded; reads as anger, contempt, concentration; style: cartoonish, monologue; average recording, quiet background; genuineness 1.7/6; vocal-burst blend 0.9/10; 19.5s, DUTCH.
2450_10026_000657 · in -29.0 dBFS · gain +9.0 dB · mls-00084
(anger, contempt, concentration · frequent disfluency, somewhat unclear, audible breath, cartoonish)onder s hands aan de witt zoû kunnen te kennen geven dat een ander ambassadeur niet onwelkom zoû wezen aan het fransche hof wees overtuigd zeide d'estrades dat de heer de lionne zoowel als de koning mijn meester volkomen bekend zijn met de schatting waarin ik u houde
full caption & clip details
A middle-aged masculine voice; delivery is normally alert, measured, slightly relaxed, fairly steady; timbre is neutral-toned, slightly dark, rough, thin; somewhat unclear, frequent disfluency, fairly narrow pitch, audible breath; affect is neutral, slightly dominant, fairly guarded; reads as anger, contempt, concentration; style: cartoonish, monologue; average recording, quiet background; genuineness 1.7/6; vocal-burst blend 0.9/10; 19.5s, DUTCH.
2450_10026_000657 · in -29.0 dBFS · gain +9.0 dB · mls-00084
(concentration, emotional numbness, malevolence malice·some disfluency, slurred, light breath, narration)in weêrwil van al zijn slimheid en menschenkennis was van espenblad toch genoeg door ydelheid verblind om deze woorden van den graaf voor een kompliment op te nemen en hy boog zich op de wellevendste wijze
full caption & clip details
A middle-aged masculine voice; delivery is normally alert, measured, slightly relaxed, fairly steady; timbre is neutral-toned, slightly dark, slightly rough, balanced body; slurred, some disfluency, fairly narrow pitch, light breath; affect is neutral, neutral stance, slightly guarded; reads as concentration, emotional numbness, malevolence malice; style: narration, monologue; average recording, quiet background; genuineness 0.2/6; vocal-burst blend 0.9/10; 14.3s, DUTCH.
2450_10026_003309 · in -28.8 dBFS · gain +8.8 dB · mls-00084
Anger ↓ / Longing ↑c-mls-AB2 · #18
This chain comes from the two-sided rule: it only counts if both emotions move — Anger down and Longing up — by at least 0.25 each.
The chain starts with Longing clearly present — 0.68, higher than 68 % of clips in this corpus — and ends with it at the very top of the corpus at 0.98, higher than 98 % of clips in this corpus. That is a total rise of 0.30.
At the same time Anger goes the other way, from 0.98 (higher than 98 % of clips in this corpus) to 0.71 (higher than 71 % of clips in this corpus), a change of -0.27. Both halves had to happen for this chain to qualify.
It takes 3 clips to get there. Clip to clip the moves are +0.15, then +0.15 — an even, steady climb — each clip carries about the same share.
No single step is larger than the 0.25 cap, which is exactly what stops this being a jump cut: the change has to be spread across the clips instead of landing all at once.
Same speaker? The least similar clip scores 0.91 against the first clip, where 1.00 would mean an identical voice. That is a strong match — almost certainly one person throughout. Neighbouring clips score at worst 0.94 against each other.
Voice consistency: these clips are separate recordings joined together. The measured match is tight (0.91), so any shift should be subtle — but you may still notice the voice change slightly from segment to segment. Voice conversion has not been applied yet in this build. A planned pass will re-render every segment onto the first segment's voice, which removes this effect entirely.
Unchanged across all 3 clips: an adult feminine voice · neutral-toned, neutral-bright, fairly smooth, balanced body, good recording, no background noise, slightly relaxed, clear
(anger, fear, impatience and irritability · normal-paced, normally alert, fairly steady, monologue)ohne weitere umschweife erklärte er sich unverzüglich bereit für alle die bauern die auf eine so unglückliche weise gestorben waren aus eigener tasche die abgaben zu entrichten dieser vorschlag versetzte pljuschkin in höchstes erstaunen er glotzte ihn lange an und fragte zuletzt
full caption & clip details
An adult feminine voice; delivery is normally alert, normal-paced, slightly relaxed, fairly steady; timbre is neutral-toned, neutral-bright, fairly smooth, balanced body; clear, no disfluency, moderate pitch range, light breath; affect is neutral, neutral stance, slightly guarded; reads as anger, fear, impatience and irritability; style: monologue, formal; good recording, no background noise; genuineness 0.2/6; vocal-burst blend 0.0/10; 19.5s, GERMAN.
10148_11442_003518 · in -28.8 dBFS · gain +8.8 dB · mls-00008
(fear, confusion, sadness· normal-paced, normally alert, fairly steady, didactic)waren sie vielleicht im militärdienst väterchen nein entgegnete tschitschikow nicht ohne list ich war nur im zivildienste im zivildienste wiederholte pljuschkin und begann die lippen zu bewegen als ob er etwas kaute
full caption & clip details
A middle-aged feminine voice; delivery is normally alert, normal-paced, slightly relaxed, fairly steady; timbre is neutral-toned, neutral-bright, fairly smooth, balanced body; clear, no disfluency, moderate pitch range, light breath; affect is mildly positive, neutral stance, slightly guarded; reads as fear, confusion, sadness; style: didactic, formal; good recording, no background noise; genuineness 0.0/6; vocal-burst blend 0.1/10; 18.6s, GERMAN.
10148_11442_003581 · in -28.8 dBFS · gain +8.8 dB · mls-00008
(longing, sadness, malevolence malice·measured, subdued, steady, didactic)wie ist es nun das wäre doch ein schaden für sie um ihnen ein vergnügen zu bereiten bin ich auch bereit den schaden auf mich zu nehmen
full caption & clip details
A middle-aged somewhat feminine voice; delivery is subdued, measured, slightly relaxed, steady; timbre is neutral-toned, neutral-bright, fairly smooth, balanced body; clear, frequent disfluency, moderate pitch range, light breath; affect is neutral, neutral stance, slightly guarded; reads as longing, sadness, malevolence malice; style: didactic, whispered; good recording, no background noise; genuineness 0.2/6; vocal-burst blend 0.7/10; 11.4s, GERMAN.
10148_11442_003849 · in -29.6 dBFS · gain +9.6 dB · mls-00008
Sourness ↓ / Infatuation ↑c-mls-AB2 · #19
This chain comes from the two-sided rule: it only counts if both emotions move — Sourness down and Infatuation up — by at least 0.25 each.
The chain starts with Infatuation clearly present — 0.73, higher than 74 % of clips in this corpus — and ends with it at the very top of the corpus at 1.00, virtually no clip in this corpus scores higher. That is a total rise of 0.26.
At the same time Sourness goes the other way, from 1.00 (virtually no clip in this corpus scores higher) to 0.74 (higher than 74 % of clips in this corpus), a change of -0.26. Both halves had to happen for this chain to qualify.
It takes 4 clips to get there. Clip to clip the moves are +0.18, then +0.05, then +0.03 — most of the change happening immediately, then levelling off.
No single step is larger than the 0.25 cap, which is exactly what stops this being a jump cut: the change has to be spread across the clips instead of landing all at once.
Same speaker? The least similar clip scores 0.77 against the first clip, where 1.00 would mean an identical voice. That is below the 0.80 threshold the mining used — treat the “same speaker” claim here with caution. Neighbouring clips score at worst 0.77 against each other.
Voice consistency: these clips are separate recordings joined together and the match is loose (0.77, under the 0.80 threshold), so the voice may audibly change between segments. Voice conversion has not been applied yet in this build. A planned pass will re-render every segment onto the first segment's voice, which removes this effect entirely.
Unchanged across all 4 clips: a middle-aged masculine voice · balanced body, measured
(sourness, malevolence malice, contentment · normally alert, neutral tension, moderately variable, storytelling)gritó con insólito buen humor es verdaderamente necesario que les dé usted un descanso á sus caballos y que entre á tomar un vaso de vino y á felicitarme
full caption & clip details
A middle-aged masculine voice; delivery is normally alert, measured, neutral tension, moderately variable; timbre is warm, slightly dark, slightly rough, balanced body; average clarity, frequent disfluency, wide pitch range, audible breath; affect is neutral, slightly dominant, slightly guarded; reads as sourness, malevolence malice, contentment; style: storytelling, cartoonish; average recording, quiet background; genuineness 3.2/6; vocal-burst blend 5.3/10; 13.1s, SPANISH.
8882_10372_000146 · in -21.7 dBFS · gain +1.7 dB · mls-00025
(sourness, emotional numbness, bitterness· normally alert, slightly relaxed, fairly steady, monologue)después de lo que había oído decir sobre la manera como erankland trataba á su hija mis sentimientos hacia él estaban lejos de ser amistosos pero deseaba despachar á perkins y al
full caption & clip details
An adult masculine voice; delivery is normally alert, measured, slightly relaxed, fairly steady; timbre is neutral-toned, slightly dark, fairly smooth, balanced body; somewhat unclear, some disfluency, fairly narrow pitch, light breath; affect is neutral, neutral stance, slightly guarded; reads as sourness, emotional numbness, bitterness; style: monologue, didactic; average recording, quiet background; genuineness 1.2/6; vocal-burst blend 4.2/10; 14.2s, SPANISH.
8882_10372_000017 · in -22.2 dBFS · gain +2.2 dB · mls-00025
(contentment, bitterness, triumph·subdued, slightly relaxed, fairly steady, monologue)para queaarme solo y la ocasión era buena bajé del carruaje y envió un recado á sir enrique haciéndole baber que regresaría á pie á tiempo para la comida después seguí á frankland hasta el comedor de su casa
full caption & clip details
An adult masculine voice; delivery is subdued, measured, slightly relaxed, fairly steady; timbre is neutral-toned, neutral-bright, fairly smooth, balanced body; somewhat unclear, some disfluency, fairly narrow pitch, light breath; affect is mildly positive, neutral stance, slightly guarded; reads as contentment, bitterness, triumph; style: monologue, didactic; average recording, quiet background; genuineness 0.6/6; vocal-burst blend 3.5/10; 17.0s, SPANISH.
8882_10372_000250 · in -22.4 dBFS · gain +2.4 dB · mls-00025
(infatuation, thankfulness gratitude, elation·normally alert, slightly relaxed, moderately variable, storytelling)hoy es un gran día para mí señor uno de los verdaderos días de fiesta de mi vida exclamó entre risitas ahogadas
full caption & clip details
A middle-aged masculine voice; delivery is normally alert, measured, slightly relaxed, moderately variable; timbre is neutral-toned, slightly dark, fairly smooth, balanced body; very clear, some disfluency, wide pitch range, audible breath; affect is neutral, slightly dominant, slightly guarded; reads as infatuation, thankfulness gratitude, elation; style: storytelling, narration; good recording, no background noise; genuineness 1.5/6; vocal-burst blend 2.6/10; 10.2s, SPANISH.
8882_10372_000554 · in -21.7 dBFS · gain +1.7 dB · mls-00025
Fatigue Exhaustion ↓ / Affection ↑c-mls-AB2 · #20
This chain comes from the two-sided rule: it only counts if both emotions move — Fatigue Exhaustion down and Affection up — by at least 0.25 each.
The chain starts with Affection clearly present — 0.60, higher than 60 % of clips in this corpus — and ends with it at the very top of the corpus at 0.98, higher than 98 % of clips in this corpus. That is a total rise of 0.38.
At the same time Fatigue Exhaustion goes the other way, from 0.99 (higher than 99 % of clips in this corpus) to 0.67 (higher than 67 % of clips in this corpus), a change of -0.32. Both halves had to happen for this chain to qualify.
It takes 3 clips to get there. Clip to clip the moves are +0.19, then +0.19 — an even, steady climb — each clip carries about the same share.
No single step is larger than the 0.25 cap, which is exactly what stops this being a jump cut: the change has to be spread across the clips instead of landing all at once.
Same speaker? The least similar clip scores 0.96 against the first clip, where 1.00 would mean an identical voice. That is a strong match — almost certainly one person throughout. Neighbouring clips score at worst 0.94 against each other.
Voice consistency: these clips are separate recordings joined together. The measured match is tight (0.96), so any shift should be subtle — but you may still notice the voice change slightly from segment to segment. Voice conversion has not been applied yet in this build. A planned pass will re-render every segment onto the first segment's voice, which removes this effect entirely.
Unchanged across all 3 clips: a child masculine voice · neutral-toned, neutral-bright, fairly smooth, balanced body, quiet background, slightly relaxed, clear, light breath
(fatigue exhaustion, disgust, distress · fast, normally alert, fairly steady, monologue)comme il n'en pouvoit plus de fatigue il s'endormit aprés s'estre reposé quelque temps et vint à ronfler si effroyablement que les pauvres enfans n'eurent pas moins de peur que quand il tenoit son grand couteau pour leur couper la gorge
full caption & clip details
A child masculine voice; delivery is normally alert, fast, slightly relaxed, fairly steady; timbre is neutral-toned, neutral-bright, fairly smooth, balanced body; clear, almost no disfluency, moderate pitch range, light breath; affect is neutral, neutral stance, slightly guarded; reads as fatigue exhaustion, disgust, distress; style: monologue, authoritative; good recording, quiet background; genuineness 0.0/6; vocal-burst blend 0.0/10; 13.4s, FRENCH.
123_131_000192 · in -31.8 dBFS · gain +11.8 dB · mls-00052
(fear, emotional numbness, distress · fast, normally alert, fairly steady, monologue)le petit poucet en eut moins de peur et dit à ses freres de s'enfuir promptement à la maison pendant que l'ogre dormoit bien fort et qu'ils ne se missent point en peine de luy
full caption & clip details
A child masculine voice; delivery is normally alert, fast, slightly relaxed, fairly steady; timbre is neutral-toned, neutral-bright, fairly smooth, balanced body; clear, almost no disfluency, moderate pitch range, light breath; affect is neutral, neutral stance, slightly guarded; reads as fear, emotional numbness, distress; style: monologue, authoritative; good recording, quiet background; genuineness 0.0/6; vocal-burst blend 0.0/10; 10.0s, FRENCH.
123_131_000087 · in -33.8 dBFS · gain +13.8 dB · mls-00052
(affection, malevolence malice, contentment·measured, subdued, steady, monologue)ils crurent son conseil et gagnerent viste la maison le petit poucet s'estant approché de l'ogre lui tira doucement ses bottes et les mit aussi
full caption & clip details
A child masculine voice; delivery is subdued, measured, slightly relaxed, steady; timbre is neutral-toned, neutral-bright, fairly smooth, balanced body; clear, frequent disfluency, fairly narrow pitch, light breath; affect is neutral, neutral stance, slightly guarded; reads as affection, malevolence malice, contentment; style: monologue, cartoonish; average recording, quiet background; genuineness 0.0/6; vocal-burst blend 0.0/10; 11.6s, FRENCH.
123_131_000193 · in -35.1 dBFS · gain +15.1 dB · mls-00052